예제 #1
0
int main(int argc, const char** argv)
{
  if (argc < 2) return 1;
  // the path to the data should be given on the command line
  String tutorial_data_path(argv[1]);
  
  IndexedMzMLFileLoader imzml;

  // load data from an indexed MzML file
  OnDiscMSExperiment<> map;
  imzml.load(tutorial_data_path + "/data/Tutorial_FileIO_indexed.mzML", map);
  // Get the first spectrum in memory, do some constant (non-changing) data processing
  MSSpectrum<> s = map.getSpectrum(0);
  std::cout << "There are " << map.getNrSpectra() << " spectra in the input file." << std::endl;
  std::cout << "The first spectrum has " << s.size() << " peaks." << std::endl;

  // store the (unmodified) data in a different file
  imzml.store("Tutorial_FileIO_output.mzML", map);

  return 0;
} //end of main
  ExitCodes main_(int, const char**) override
  {
    //-------------------------------------------------------------
    // parameter handling
    //-------------------------------------------------------------

    String in = getStringOption_("in");
    String out = getStringOption_("out");

    IndexedMzMLFileLoader loader; 

    //-------------------------------------------------------------
    // loading input
    //-------------------------------------------------------------
    OnDiscPeakMap exp;
    loader.load(in, exp);

    // We could write out this warning in the constructor if no spectra have come our way ...
    /*
    if (ms_exp_raw.empty() && ms_exp_raw.getChromatograms().size() == 0)
    {
      LOG_WARN << "The given file does not contain any conventional peak data, but might"
                  " contain chromatograms. This tool currently cannot handle them, sorry.";
      return INCOMPATIBLE_INPUT_DATA;
    }
    */

    // We could check with the first spectrum that we process whether it fulfills the requirements
    // check for peak type (profile data required)
    /*
    if (!ms_exp_raw.empty() && PeakTypeEstimator().estimateType(ms_exp_raw[0].begin(), ms_exp_raw[0].end()) == SpectrumSettings::CENTROID)
    {
      writeLog_("Warning: OpenMS peak type estimation indicates that this is not profile data!");
    }
    */

    // We can check each spectrum and throw an error if it is not sorted
    // check if spectra are sorted
    /*
    for (Size i = 0; i < ms_exp_raw.size(); ++i)
    {
      if (!ms_exp_raw[i].isSorted())
      {
        writeLog_("Error: Not all spectra are sorted according to peak m/z positions. Use FileFilter to sort the input!");
        return INCOMPATIBLE_INPUT_DATA;
      }
    }
    */

    // We can check each chromatogram and throw an error if it is not sorted
    //check if chromatograms are sorted
    /*
    for (Size i = 0; i < ms_exp_raw.getChromatograms().size(); ++i)
    {
      if (!ms_exp_raw.getChromatogram(i).isSorted())
      {
        writeLog_("Error: Not all chromatograms are sorted according to peak m/z positions. Use FileFilter to sort the input!");
        return INCOMPATIBLE_INPUT_DATA;
      }
    }
    */

    //-------------------------------------------------------------
    // pick
    //-------------------------------------------------------------
    PeakMap ms_exp_peaks;

    ///////////////////////////////////
    // Create PeakPickerHiRes and hand it to the PPHiResMzMLConsumer
    ///////////////////////////////////
    Param pepi_param = getParam_().copy("algorithm:", true);
    writeDebug_("Parameters passed to LowMemPeakPickerHiRes", pepi_param, 3);

    PeakPickerHiRes pp;
    pp.setLogType(log_type_);
    pp.setParameters(pepi_param);
    pp.pickExperiment(exp, ms_exp_peaks);

    //-------------------------------------------------------------
    // writing output
    //-------------------------------------------------------------
    //annotate output with data processing info
    addDataProcessing_(ms_exp_peaks, getProcessingInfo_(DataProcessing::PEAK_PICKING));

    MzMLFile mz_data_file;
    mz_data_file.setLogType(log_type_);
    mz_data_file.store(out, ms_exp_peaks);

    return EXECUTION_OK;
  }
예제 #3
0
  ExitCodes main_(int, const char**) override
  {
    //-------------------------------------------------------------
    // parameter handling
    //-------------------------------------------------------------

    //input file names
    String in = getStringOption_("in");
    String read_method = getStringOption_("read_method");
    bool load_data = getStringOption_("loadData") == "true";

    if (read_method == "streaming")
    {
      std::cout << "Read method: streaming" << std::endl;

      // Create the consumer, set output file name, transform
      TICConsumer consumer;
      MzMLFile mzml;
      mzml.setLogType(log_type_);

      PeakFileOptions opt = mzml.getOptions();
      opt.setFillData(load_data); // whether to actually load any data
      opt.setSkipXMLChecks(true); // save time by not checking base64 strings for whitespaces 
      opt.setMaxDataPoolSize(100);
      opt.setAlwaysAppendData(false);
      mzml.setOptions(opt);
      mzml.transform(in, &consumer, true, true);

      std::cout << "There are " << consumer.nr_spectra << " spectra and " << consumer.nr_peaks << " peaks in the input file." << std::endl;
      std::cout << "The total ion current is " << consumer.TIC << std::endl;
      size_t after;
      SysInfo::getProcessMemoryConsumption(after);
      std::cout << " Memory consumption after " << after << std::endl;
    }
    else if (read_method == "regular")
    {
      std::cout << "Read method: regular" << std::endl;

      MzMLFile mzml;
      mzml.setLogType(log_type_);
      PeakFileOptions opt = mzml.getOptions();
      opt.setFillData(load_data); // whether to actually load any data
      opt.setSkipXMLChecks(true); // save time by not checking base64 strings for whitespaces 
      mzml.setOptions(opt);
      PeakMap map;
      mzml.load(in, map);
      double TIC = 0.0;
      long int nr_peaks = 0;
      for (Size i =0; i < map.size(); i++)
      {
        nr_peaks += map[i].size();
        for (Size j = 0; j < map[i].size(); j++)
        {
          TIC += map[i][j].getIntensity();
        }
      }

      std::cout << "There are " << map.size() << " spectra and " << nr_peaks << " peaks in the input file." << std::endl;
      std::cout << "The total ion current is " << TIC << std::endl;
      size_t after;
      SysInfo::getProcessMemoryConsumption(after);
      std::cout << " Memory consumption after " << after << std::endl;
    }
    else if (read_method == "indexed")
    {
      std::cout << "Read method: indexed" << std::endl;
      
      IndexedMzMLFileLoader imzml;
      // load data from an indexed MzML file
      OnDiscPeakMap map;
      imzml.load(in, map);
      double TIC = 0.0;
      long int nr_peaks = 0;
      if (load_data)
      {
        for (Size i =0; i < map.getNrSpectra(); i++)
        {
          OpenMS::Interfaces::SpectrumPtr sptr = map.getSpectrumById(i);

          nr_peaks += sptr->getIntensityArray()->data.size();
          TIC += std::accumulate(sptr->getIntensityArray()->data.begin(), sptr->getIntensityArray()->data.end(), 0.0);
        }
      }

      std::cout << "There are " << map.getNrSpectra() << " spectra and " << nr_peaks << " peaks in the input file." << std::endl;
      std::cout << "The total ion current is " << TIC << std::endl;
      size_t after;
      SysInfo::getProcessMemoryConsumption(after);
      std::cout << " Memory consumption after " << after << std::endl;
    }
    else if (read_method == "indexed_parallel")
    {
      std::cout << "Read method: indexed (parallel)" << std::endl;
      
      IndexedMzMLFileLoader imzml;
      PeakFileOptions opt = imzml.getOptions();
      opt.setFillData(load_data); // whether to actually load any data
      imzml.setOptions(opt);

      // load data from an indexed MzML file
      OnDiscPeakMap map;
      map.openFile(in, true);
      map.setSkipXMLChecks(true);

      double TIC = 0.0;
      long int nr_peaks = 0;

      if (load_data)
      {

        // firstprivate means that each thread has its own instance of the
        // variable, each copy initialized with the initial value 
#ifdef _OPENMP
#pragma omp parallel for firstprivate(map) 
#endif
        for (SignedSize i =0; i < (SignedSize)map.getNrSpectra(); i++)
        {
          OpenMS::Interfaces::SpectrumPtr sptr = map.getSpectrumById(i);
          double nr_peaks_l = sptr->getIntensityArray()->data.size();
          double TIC_l = std::accumulate(sptr->getIntensityArray()->data.begin(), sptr->getIntensityArray()->data.end(), 0.0);
#ifdef _OPENMP
#pragma omp critical (indexed)
#endif
          {
            TIC += TIC_l;
            nr_peaks += nr_peaks_l;
          }
        }

      }

      std::cout << "There are " << map.getNrSpectra() << " spectra and " << nr_peaks << " peaks in the input file." << std::endl;
      std::cout << "The total ion current is " << TIC << std::endl;
      size_t after;
      SysInfo::getProcessMemoryConsumption(after);
      std::cout << " Memory consumption after " << after << std::endl;
    }
    else if (read_method == "cached")
    {
      std::cout << "Read method: cached" << std::endl;

      // Special handling of cached mzML as input types: 
      // we expect two paired input files which we should read into exp
      std::vector<String> split_out;
      in.split(".cachedMzML", split_out);
      if (split_out.size() != 2)
      {
        LOG_ERROR << "Cannot deduce base path from input '" << in << 
          "' (note that '.cachedMzML' should only occur once as the final ending)" << std::endl;
        return ILLEGAL_PARAMETERS;
      }
      String in_meta = split_out[0] + ".mzML";

      MzMLFile f;
      f.setLogType(log_type_);
      CachedmzML cacher;
      cacher.setLogType(log_type_);

      CachedmzML cache;
      cache.createMemdumpIndex(in);
      const std::vector<std::streampos> spectra_index = cache.getSpectraIndex();

      std::ifstream ifs_;
      ifs_.open(in.c_str(), std::ios::binary);

      double TIC = 0.0;
      long int nr_peaks = 0;
      for (Size i=0; i < spectra_index.size(); ++i)
      {

        BinaryDataArrayPtr mz_array(new BinaryDataArray);
        BinaryDataArrayPtr intensity_array(new BinaryDataArray);
        int ms_level = -1;
        double rt = -1.0;
        ifs_.seekg(spectra_index[i]);
        CachedmzML::readSpectrumFast(mz_array, intensity_array, ifs_, ms_level, rt);

        nr_peaks += intensity_array->data.size();
        for (Size j = 0; j < intensity_array->data.size(); j++)
        {
          TIC += intensity_array->data[j];
        }
      }

      std::cout << "There are " << spectra_index.size() << " spectra and " << nr_peaks << " peaks in the input file." << std::endl;
      std::cout << "The total ion current is " << TIC << std::endl;
      size_t after;
      SysInfo::getProcessMemoryConsumption(after);
      std::cout << " Memory consumption after " << after << std::endl;
    }
    else if (read_method == "cached_parallel")
    {
      std::cout << "Read method: cached parallel" << std::endl;

      // Special handling of cached mzML as input types: 
      // we expect two paired input files which we should read into exp
      std::vector<String> split_out;
      in.split(".cachedMzML", split_out);
      if (split_out.size() != 2)
      {
        LOG_ERROR << "Cannot deduce base path from input '" << in << 
          "' (note that '.cachedMzML' should only occur once as the final ending)" << std::endl;
        return ILLEGAL_PARAMETERS;
      }
      String in_meta = split_out[0] + ".mzML";

      MzMLFile f;
      f.setLogType(log_type_);
      CachedmzML cacher;
      cacher.setLogType(log_type_);

      CachedmzML cache;
      cache.createMemdumpIndex(in);
      const std::vector<std::streampos> spectra_index = cache.getSpectraIndex();

      FileAbstraction filestream(in);

      double TIC = 0.0;
      long int nr_peaks = 0;
#ifdef _OPENMP
#pragma omp parallel for firstprivate(filestream) 
#endif
      for (SignedSize i=0; i < (SignedSize)spectra_index.size(); ++i)
      {
        BinaryDataArrayPtr mz_array(new BinaryDataArray);
        BinaryDataArrayPtr intensity_array(new BinaryDataArray);
        int ms_level = -1;
        double rt = -1.0;
        // we only change the position of the thread-local filestream
        filestream.getStream().seekg(spectra_index[i]);
        CachedmzML::readSpectrumFast(mz_array, intensity_array, filestream.getStream(), ms_level, rt);

        double nr_peaks_l = intensity_array->data.size();
        double TIC_l = std::accumulate(intensity_array->data.begin(), intensity_array->data.end(), 0.0);
#ifdef _OPENMP
#pragma omp critical (indexed)
#endif
        {
          TIC += TIC_l;
          nr_peaks += nr_peaks_l;
        }
      }

      std::cout << "There are " << spectra_index.size() << " spectra and " << nr_peaks << " peaks in the input file." << std::endl;
      std::cout << "The total ion current is " << TIC << std::endl;
      size_t after;
      SysInfo::getProcessMemoryConsumption(after);
      std::cout << " Memory consumption after " << after << std::endl;
    }

    return EXECUTION_OK;
  }